Hello

nGreetings from ZettaMine Labs Pvt Ltd!!

n

nWe are looking for LLM and Agentic Security expert (Data exfiltration specialization) for PAN India.

n

nJob Role : LLM and Agentic Security expert (Data exfiltration specialization)

nLocation : PAN India

nNotice Period : NA( Freelancing allowed)

nExperience : 6 years or above

nRelevant Exp : Minimum of 4 Years Experience in below list of skills

n

n✓ LLM and AI agent Security testing

n✓ Experience in Data exfiltration attacks

n✓ LLM architecture & training process knowledge

n✓ OWASP LLM Top 10 & MITRE ATLAS

n✓ Adversarial prompt design & execution

n✓ Vulnerability assessment for AI/ML systems

n✓ Prompt injection & jailbreaking techniques

n✓ Offensive security tooling & methodology

n✓ Role-playing and bias exploitation attacks

n✓ Security reporting and findings documentation

n

nMandatory :

n

n

n
- 4+ years of experience in offensive security, AI/ML security research, penetration testing of AI systems, or dedicated LLM red-teaming.
n
- Good Experience in data exfiltration vulnerability testing of LLMs and Agentic systems
n
- Deep working knowledge of LLM architecture, training processes, and alignment techniques (RLHF, fine-tuning, instruction-following).
n
- Proven hands-on expertise in adversarial prompt design, jailbreaking, prompt injection, and role-play attack methodologies.
n
- Strong grounding in cybersecurity principles applied to AI/ML systems; familiarity with OWASP LLM Top 10 and related frameworks.
n
- Transparent and precise written communication skills — ability to document technical findings thoroughly and present security risks to non-technical stakeholders.
n




- Commitment to responsible testing practices and understanding of the ethical implications of AI security research.
n

n

n:

nAs an LLM and Agentic Security expert (Data exfiltration specialization) , you will be the adversarial mind that frontier AI systems need but rarely have. Your mandate is to rigorously probe large language models for security vulnerabilities — designing, executing, and documenting adversarial prompt campaigns that expose real failure modes before bad actors find them first. You will operate at the intersection of offensive security and AI research , crafting sophisticated attack vectors including prompt injection, jailbreaking, role-play manipulation, and bias exploitation, and translating findings into actionable security intelligence for AI development teams.

n

nThis is not a compliance checkbox role. It requires genuine adversarial creativity, deep LLM knowledge, and the discipline to document what you find with rigour and ethical clarity.

n

nKey Responsibilities:

n

nAdversarial Prompt Engineering & Attack Design

n

n
- Develop and execute a structured suite of adversarial prompts — from foundational to highly sophisticated — targeting known and emerging LLM vulnerability classes
n




- Design attacks to bypass safety filters and content moderation policies; induce leakage of sensitive or confidential information; manipulate outputs toward harmful, biased, or unintended content
n
- Engineer prompt injection, jailbreaking, role-playing, and model bias exploitation scenarios; test against a spectrum of LLM architectures and deployment configurations
n

n

nSecurity Evaluation & Vulnerability Analysis

n

n
- Systematically execute adversarial test campaigns against target LLMs; analyse responses to identify successful exploits, failure patterns, and exploitable security weaknesses
n
- Conduct vulnerability assessments against published frameworks including OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF; document findings with reproducible methodology
n
- Assess the resilience of safety mechanisms including RLHF alignment, Constitutional AI, and fine-tuning guardrails against adversarial pressure.
n

n

nReporting, Standards & Collaboration

n

n
- Produce clear, technically precise vulnerability reports including exploit documentation, impact assessment, and remediation recommendations
n
- Collaborate with AI development and red-team leads to translate findings into security requirements, test standards, and policy updates
n
- Contribute to Platina’s growing adversarial evaluation library and internal red-teaming playbooks.
n

n

nPlease provide following detail along with your updated profile to

n

nPrimary Skill -

nTotal Experience -

nRelevant Experience :

nCurrent location

nHighest Qualification:

nExpertise/Stream:

nDomain :

n

nI will be reaching out to you over a call or email as soon as possible.

n

nThanks & Regards,

nVyshnavi

n

📌 LLM and Agentic Security expert (Data exfiltration specialization) (Junagadh)
🏢 ZettaMine Labs
📍 Junagadh